The Key Laboratory of Agricultural Information Technology of Jiangxi Provincial Colleges and Universities was established in July 2008 with the approval of the Jiangxi Provincial Department of Education, supported by the School of Software of Jiangxi Agricultural University. Guided by the national strategic needs, relying on modern information technologies such as big data, artificial intelligence, Internet of Things, and blockchain, and focusing on combining the comprehensive educational advantages of Jiangxi Agricultural University and the actual development of information technology in China, the laboratory has formed four major research directions with distinctive fields and outstanding characteristics:
(1) Agricultural informatization and smart agriculture:This direction aims to use numerical computing, machine learning, computer graphics technology, and plant phenomorphology research to establish a visual measurement system for the dynamic growth of crops based on physiological and ecological factors, and realize the digital cultivation, detection and picking of crops with the help of computers, so as to provide basic technical means for agricultural modernization.
(2) Internet of Things and detection technology:This direction develops the Internet of Things software and hardware system in the process of data collection, transmission, processing and storage in product production and testing, and serves the system for actual agricultural production, reduces product production and testing costs, and improves product quality and production efficiency.
(3) Big data and computational intelligence:This direction uses big data analysis and computational intelligence methods and technologies to mine, analyze and reason high-dimensional complex data, discover potentially valuable knowledge, and provide new ideas and strategies for the analysis and processing of big data.
(4) Artificial intelligence and pattern recognition:This direction uses artificial intelligence and pattern recognition technologies such as computer vision, machine learning, deep learning, and human-computer interaction to detect the saliency of visual information, image classification, object detection, image segmentation, weather prediction, visual measurement, and information recognition of pest and disease characteristics.
